© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9151
    Prev
    Next
    INDEX
    Explanations

    W/Wa/Wak followed by 'a', 'az', 'ir', 'k'

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    opr
    -0.10
    çªĹå¤ĸ
    -0.10
    èĥİ
    -0.09
    ombo
    -0.09
    ãģĨãģ¾ãģı
    -0.09
    ä¸įèĪį
    -0.09
    å¹ķ
    -0.09
    ORY
    -0.09
    è¿ĺä¸įæĺ¯
    -0.09
    æµģæĺŁ
    -0.09
    POSITIVE LOGITS
    ÑĢиÑģ
    0.09
    /or
    0.09
    leys
    0.09
    papers
    0.08
    åŃļ
    0.08
    ç²¹
    0.08
    èĩªä¹ł
    0.08
    íĴĪ
    0.08
    é£ı
    0.08
     Bout
    0.08
    Activations Density 0.046%

    No Known Activations